AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

SalDiff-DTM: A Novel Dual-Temporal Modulated Diffusion Model for Omnidirectional Images Scanpath Prediction

Xiaohui Kong, Qian Liu, Dandan Zhu, Kaiwei Zhang, Xiongkuo Min

AAAI 2026 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add dual (semantic + image) GCN features (ablation)SalDiff-DTM · Salient360!REC: 4.334 -> 4.384Improved
add dual GCN features (ablation)SalDiff-DTM · AOIREC: 4.216 -> 4.226Improved
use only semantic-level or only image-level GCN instead of none (ablation)SalDiff-DTM · Salient360! and AOIREC: Salient360! 4.334 -> 4.317 / 4.331; AOI 4.216 -> 4.188 / 4.183Hurt
add BiLSTM feature (ablation)SalDiff-DTM · Salient360!REC: 4.340 -> 4.384Improved
add BiLSTM feature (ablation)SalDiff-DTM · AOIREC: 4.203 -> 4.226Improved
add both BiMamba and M3 blocks (TABiMamba) instead of neither (ablation)SalDiff-DTM · Salient360!REC: 4.331 -> 4.384Improved
add both BiMamba and M3 blocks instead of neither (ablation)SalDiff-DTM · AOIREC: 4.177 -> 4.226Improved
use SalDiff-DTM instead of ScanDMMscanpath predictor · Salient360!REC: 3.403 -> 4.384Improved
use SalDiff-DTM instead of ScanDMMscanpath predictor · SitzmannDTW: 1953.319 -> 1984.446Hurt
use SalDiff-DTM instead of Pathformer3Dscanpath predictor · Salient360!DTW: 1645.650 -> 1552.055Improved
use SalDiff-DTM instead of ScanDMM (efficiency)scanpath predictor · Sitzmann testinference latency (s): 0.2887 -> 0.2537Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy